© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6606
    Prev
    Next
    INDEX
    Explanations

    terms related to grievances and appeals within a correctional or administrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hierarchical position

    np_acts-logits-general · gemini-2.0-flash

    levels and hierarchy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.33
    pgterms
    -0.31
    spół
    -0.31
     Umbau
    -0.31
    tagHelperRunner
    -0.30
    teln
    -0.30
    PropertyChanging
    -0.30
     censiti
    -0.29
    Cj
    -0.29
     Substanz
    -0.29
    POSITIVE LOGITS
     levels
    1.23
     hierarchy
    1.16
     level
    1.16
     higher
    1.13
     Levels
    1.05
     tiers
    1.05
     hierarchical
    1.02
     tier
    1.02
    higher
    1.01
     lower
    0.99
    Activations Density 0.823%

    No Known Activations